From 7a3f93135276b438ba77bed9978b070a29e342a9 Mon Sep 17 00:00:00 2001
From: Liang-Chi Hsieh <viirya@gmail.com>
Date: Wed, 10 Jul 2024 12:58:22 -0700
Subject: [PATCH] test: Run optimized version of q72 derived from TPC-DS

---
 .../src/test/resources/tpcds-extended/q72.sql | 26 +++++++++++++++++++
 .../spark/sql/CometTPCDSQueryTestSuite.scala  | 15 +++++++++++
 2 files changed, 41 insertions(+)
 create mode 100644 spark/src/test/resources/tpcds-extended/q72.sql

diff --git a/spark/src/test/resources/tpcds-extended/q72.sql b/spark/src/test/resources/tpcds-extended/q72.sql
new file mode 100644
index 0000000000..4c95c8aa7a
--- /dev/null
+++ b/spark/src/test/resources/tpcds-extended/q72.sql
@@ -0,0 +1,26 @@
+select  i_item_desc
+      ,w_warehouse_name
+      ,d1.d_week_seq
+      ,sum(case when p_promo_sk is null then 1 else 0 end) no_promo
+      ,sum(case when p_promo_sk is not null then 1 else 0 end) promo
+      ,count(*) total_cnt
+from catalog_sales
+join date_dim d1 on (cs_sold_date_sk = d1.d_date_sk)
+join customer_demographics on (cs_bill_cdemo_sk = cd_demo_sk)
+join household_demographics on (cs_bill_hdemo_sk = hd_demo_sk)
+join item on (i_item_sk = cs_item_sk)
+join inventory on (cs_item_sk = inv_item_sk)
+join warehouse on (w_warehouse_sk=inv_warehouse_sk)
+join date_dim d2 on (inv_date_sk = d2.d_date_sk)
+join date_dim d3 on (cs_ship_date_sk = d3.d_date_sk)
+left outer join promotion on (cs_promo_sk=p_promo_sk)
+left outer join catalog_returns on (cr_item_sk = cs_item_sk and cr_order_number = cs_order_number)
+where d1.d_week_seq = d2.d_week_seq
+  and inv_quantity_on_hand < cs_quantity 
+  and d3.d_date > d1.d_date + 5
+  and hd_buy_potential = '501-1000'
+  and d1.d_year = 1999
+  and cd_marital_status = 'S'
+group by i_item_desc,w_warehouse_name,d1.d_week_seq
+order by total_cnt desc, i_item_desc, w_warehouse_name, d_week_seq
+LIMIT 100
diff --git a/spark/src/test/scala/org/apache/spark/sql/CometTPCDSQueryTestSuite.scala b/spark/src/test/scala/org/apache/spark/sql/CometTPCDSQueryTestSuite.scala
index c2b853515a..6aec042af9 100644
--- a/spark/src/test/scala/org/apache/spark/sql/CometTPCDSQueryTestSuite.scala
+++ b/spark/src/test/scala/org/apache/spark/sql/CometTPCDSQueryTestSuite.scala
@@ -35,6 +35,8 @@ import org.apache.spark.sql.test.TestSparkSession
  */
 class CometTPCDSQueryTestSuite extends QueryTest with TPCDSBase with CometSQLQueryTestHelper {
 
+  val tpcdsExtendedQueries: Seq[String] = Seq("q72")
+
   private val tpcdsDataPath = sys.env.get("SPARK_TPCDS_DATA")
 
   private val regenGoldenFiles: Boolean = System.getenv("SPARK_GENERATE_GOLDEN_FILES") == "1"
@@ -224,6 +226,19 @@ class CometTPCDSQueryTestSuite extends QueryTest with TPCDSBase with CometSQLQue
         }
       }
     }
+
+    tpcdsExtendedQueries.foreach { name =>
+      val queryString = resourceToString(
+        s"tpcds-extended/$name.sql",
+        classLoader = Thread.currentThread().getContextClassLoader)
+      test(s"extended $name") {
+        val goldenFile = new File(s"$baseResourcePath/extended", s"$name.sql.out")
+        joinConfs.foreach { conf =>
+          System.gc() // SPARK-37368
+          runQuery(queryString, goldenFile, conf)
+        }
+      }
+    }
   } else {
     ignore("skipped because env `SPARK_TPCDS_DATA` is not set") {}
   }